Showing papers in "Pattern Recognition Letters in 1997"

TL;DR: In this paper a particular cost function for graph edit distance is introduced, and it is shown that under this cost functiongraph edit distance computation is equivalent to the maximum common subgraph problem.

TL;DR: Recent advances in speaker recognition technology include VQ- and ergodic-HMM-based text-independent recognition methods, a text-prompted recognition method, parameter/distance normalization and model adaptation techniques, and methods of updating models and a priori thresholds in speaker verification.

TL;DR: This paper proposes an improved seeded region growing algorithm that retains the advantages of the Adams and Bischof algorithm - fast execution, robust segmentation, and no tuning parameters - but is pixel order independent.

TL;DR: This study is distinguished from other studies by treating algorithms selected from distinct technique groups as well as using carefully designed synthetic images for the test experiments, which makes this study a general and effective one for revealing the performance of segmentation algorithms.

TL;DR: A new entropy of a fuzzy set is defined based on the membership functions of the intersection and union of the set and its complement set and the concept of fuzzy cross-entropy is introduced.

TL;DR: This approach detects a linear pattern in preprocessed images via model-based clustering using an approximate Bayes factor which provides a criterion for assessing the evidence for the presence of a defect.

TL;DR: This method of outlier handling combined with the classifier is applied to the well-known problem of automatic, constrained classification of chromosomes into their biological classes and it is shown that it decreases the error rate relative to the classical, normal, model by more than 50%.

TL;DR: The Gabriel and Relative Neighbourhood graphs are used to select a suitable subset of prototypes for the Nearest Neighbour rule and its performance is compared to those obtained by classical techniques.

TL;DR: It is shown that a particular case of the Bayesian Ying–Yang learning system and theory reduces to the maximum likelihood learning of a finite mixture, from which the EM algorithm for its parameter estimation and its various approximate but fast algorithms for clustering in general cases are obtained.

TL;DR: The hierarchical clustering scheme is shown to obtain near-global optimal results with low computational load, and was demonstrated in the past to obtain global optimal results, but with high computational load.

TL;DR: An overview of the current status of multivariate probability models research with particular attention to recent developments which have served to unify such seemingly disparate topics as probabilistic expert systems, statistical physics, image analysis, genetics, decoding of error-correcting codes, Kalman filters, and speech recognition with Markov models.

TL;DR: A new approach to extracting periodicity of a regular texture based on autocorrelation functions is proposed, which needs no preprocessing and keeps tolerant to distortions in the texture, such as noises, intensity changes, and geometric variants.

TL;DR: A methodology for fusing multiple instances of biometric data to improve the performance of a personal identity verification system is developed and it is shown that the fusion based on rank order statistic, i.e., the median, is robust to outliers.

TL;DR: The proposed method is applicable for clustering tasks where clusters are crisp and spherical and determines the number of clusters and the cluster centers in such a way that locally optimal solutions are avoided.

TL;DR: The person authentication system SESAM is described, which combines three different biometric cues to reach robust identification and verification, and a field test is done to show that this approach leads to a reliable people authentication system.

TL;DR: A new algorithm is proposed with a homogeneity criterion based on an adequate tuning between spatial neighbourhood and histogram neighbourhood that differs from other techniques by reconsidering the pixel assignments on each step by a process which minimizes variance through special dilations.

TL;DR: This paper aims to compare some approaches to implement Sammon's mapping on a neural network and finds that some approaches are more efficient than others.

TL;DR: The paper shows that a continuous classification can improve the performance of fingerprint retrieval tasks significantly and is based on the extraction of numerical vectors from the directional images of the fingerprints.

TL;DR: In this article, alternative non-parametric classification schemes, which come from the use of different definitions of neighbourhood, are introduced, in particular, the Nearest Centroid Neighbourhood along with the neighbourhood relation derived from the Gabriel Graph and the Relative Neighborhood Graph are used to define the corresponding (k-)Nearest Neighbour-like classifiers.

TL;DR: An approach for normalizing and mapping different modalities onto a common confidence interval and a novel method for integrating the scores of multiple classifiers for speaker verification are described.

TL;DR: A framework for comparing texture classification algorithms is proposed that consists of several suites of texture classification problems, a standard functionality for algorithms, and a method for computing a score for each algorithm.

TL;DR: An algorithm functioning as a supervisor module in a multi-expert decision making machine that uses the Bayes theory in order to estimate the biases of individual expert opinions is presented.

TL;DR: The results obtained on an optical remote-sensing data set suggest that not only is the proposed technique effective in terms of training speed but it also allows classification results to be more stable with respect to initial weights.

TL;DR: A new method for recognizing white line markings for navigation of an autonomous vehicle that operates in out-door environments is presented, implemented on the THMR-III mobile robot and experiments show that this method is robust to noise and environment changes.

TL;DR: This project outlines the project on image coding for mobile wireless environments and investigates hierarchical data structures and related algorithms, and preliminary results are encouraging.

TL;DR: A novel method to detect three-dimensional objects in arbitrary poses and sizes from a complex image and to simultaneously measure their poses and size using appearance matching is proposed.

TL;DR: This paper discusses the possibility to construct classifiers entirely based on distances or similarities, without a relation with the feature space, as an alternative to automatic pattern recognition.

TL;DR: A system for segmenting and understanding text and mathematical expressions in a document can be divided into six stages: page segmentation and labeling, character segmentation, feature extraction, character recognition, expression formation, and error correction and expression extraction.

TL;DR: A new system to segment and label CT/MRI brain slices using feature extraction and unsupervised clustering is presented, which demonstrates the power of this approach to volume segmentation of medical images.

TL;DR: The Bayesian framework is used to construct an inference matrix which can be used to gauge the mutual consistency of multiple graph-matches and is realised as an iterative discrete relaxation process which aims to maximise the elements of the inference matrix.